With the high penetration of renewable energy resources on the demand side, peer-to-peer
(P2P) energy sharing has emerged as a promising method for consuming the surplus …

In this paper, we provide a comprehensive survey of the recent advances in abnormality
detection in smart grids using multimodal image data, which include visible light, infrared …

With dramatic breakthroughs in recent years, machine learning is showing great potential to
upgrade the toolbox for power system optimization. Understanding the strength and …

The data mining method is limited to be applied in the distribution network fault diagnosis
because of the unbalanced fault sample problem. Aiming at this problem, combining the …

Conventional analysis methods cannot fully meet the business needs of power grids. At
present, several artificial intelligence (AI) projects in a single business field are competing …

Accurate faulted-phase classification for transmission lines is important to ensure the power
systems security, and the machine learning-based methods were widely studied because of …

The increasing penetration of renewable energy resources in power systems inadvertently
leads to a surge in the number of random states. The calculation of optimal load shedding …

The targets to be detected in aerial inspection images are easily affected by complex
background and partial occlusion, which makes it difficult for traditional algorithms to detect …

针对CNN 在配电网高阻故障时分类准确率低的问题, 提出了一种将CNN 和SVM
相结合的配电网故障分类研究方法. 首先将故障数据转换为时频谱灰度图 …

针对航拍巡检图像中待检测目标易受复杂背景和部分遮挡影响而造成传统算法难以准确检测的
问题, 提出一种基于卷积块注意模型的YOLOv3 输电线路故障检测方法. 首先, 在YOLOv3 …